Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2418 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.6275. Min Act: -0.0000

Data Index: 1528468 (Python Code)

Max Activating Token Index: 1004

Text #1

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.8896. Min Act: -0.0000

Data Index: 1373305 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.6043. Min Act: -0.0000

Data Index: 1518121 (Python Code)

Max Activating Token Index: 182

Text #3

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.5979. Min Act: -0.0000

Data Index: 1427754 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.7616. Min Act: -0.0000

Data Index: 1580391 (Python Code)

Max Activating Token Index: 652

Text #5

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.4632. Min Act: -0.0000

Data Index: 1481480 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.4269. Min Act: -0.0000

Data Index: 1544621 (Python Code)

Max Activating Token Index: 1014

Text #7

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.4177. Min Act: -0.0000

Data Index: 1575773 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.3890. Min Act: -0.0000

Data Index: 1647644 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.3763. Min Act: -0.0000

Data Index: 1405385 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.5288. Min Act: -0.0000

Data Index: 1440275 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.3641. Min Act: -0.0000

Data Index: 1376509 (Python Code)

Max Activating Token Index: 692

Text #12

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.3434. Min Act: -0.0000

Data Index: 1534036 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.4488. Min Act: -0.0000

Data Index: 1418934 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.2451. Min Act: -0.0000

Data Index: 1449791 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.3631. Min Act: -0.0000

Data Index: 1587360 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.1975. Min Act: -0.0000

Data Index: 1588925 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.2005. Min Act: -0.0000

Data Index: 1400630 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.1934. Min Act: -0.0000

Data Index: 1489682 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.1747. Min Act: -0.0000

Data Index: 1388584 (Python Code)

Max Activating Token Index: 700